Kablosuz manyetik sensörler kullanarak karar ağacı algoritma tabanlı araç sınıflandırmasının gerçekleştirilmesi

Year 2018, Volume: 24 Issue: 2, 302 - 310, 30.04.2018

Sercan Vançin , Ebubekir Erdem

Abstract

Kablosuz
sensör ağları kullanarak akıllı ulaşım sistemleri (Intelligent Transportation
Systems, ITS) tasarlamak, hem maliyet hem de enerji verimliliği açısından
avantajlı olup herhangi bir yolun trafiğini gözlemlemek, o yol hakkında trafik
bilgisi edinmek veya sadece araçları tespit edip tipleri ve hızlarını saptamak
son zamanlarda araştırmacıların ilgi odağı haline gelmiştir. Bu çalışmada
sensör düğümü, manyetometre, güç kartı ve pilden oluşan ve diğer çalışmalarda
kullanılan düğümlerden daha doğru ve anlaşılır veriler sunabilen bir sensör
devresi kullanılmıştır. Bu sensör devreleri ile aracın tipini belirlemek için
iki farklı yöntem sunulmuştur. İlk yöntemde, yoldan geçen araçlar, önerilen
algoritma ve



















 (Manyetik İmza Uzunluğu) paremetresine göre
otomobil, minibus, otobüs ve kamyon olarak sınıflandırılmıştır. Bu yöntemle
elde edilen doğruluk payı %89 olmuştur. Diğer yöntemde ise araç
sınıflandırması, makine öğrenmesi algoritması olan J48 kullanılarak yapılmış ve
önerilen yöntem esas alınarak elde edilen sonuçların eniyilemesi yapılmıştır.
Bir makine öğrenmesi yazılım paketi olan Weka'da uygulanan J48 sınıflandırma
algoritmasını kullanır. Karar ağacı modeli, 3 eksenli HMC5983L manyetik
sensöründen geçen araçlardan çıkarılan manyetik ham veri, ölçüm süresi gibi bir
dizi özellikten oluşturulmuştur. Özellikler, çapraz geçerlilik temelinde
değişen sınıflandırma oranları derecelerine sahip bir karar ağacı modeli
üretmek için J48 eğitim algoritmasına doğru sınıflandırmalarla sağlanan
niteliklerdir. Makine öğrenmesi algoritması olan J48 kullanımı araç
sınıflandırmasında daha verimli ve doğru sonuçlar verdiği görülmüştür. İlk yöntemle elde edilen

 değerleri hesaplama aşamasında zorluklar
doğurmuştur. Ancak J48 algoritması kullanılarak daha belirgin ve hassas sınır
ve eşik değerleri elde edilmiştir. Çalışmanın sonucu, araç sınıflandırma
sisteminde önerilen algoritmanın eniyilemesiyle yaklaşık % 100 doğruluk payı
ile etkili ve verimli olduğunu göstermektedir.

Keywords

Kablosuz sensör ağları, Manyetik sensör, Araç sınıflandırması, Makine öğrenmesi algoritması, Manyetik imza uzunluğu

Implementation of the vehicle classification based-on decision tree algorithm using wireless magnetic sensors

Abstract

The
design of Intelligent Transportation Systems (ITS) using wireless sensor
networks to observe any road traffic, get road information, or just identify
road vehicles has recently become an interesting and popular research topic
because of its advantages in cost and energy efficiency. To perform this study,
sensor circuit consisting of sensor node, magnetometer, power board and
battery, is used. This sensor structure presents more accurate and intelligible
results than sensor nodes used in other studies. Two different methods have
been proposed to determine the type of vehicle with these sensor circuits. In
the first method, vehicles passing by the road are classified as cars,
minibuses, buses and trucks according to the proposed algorithm and



















 (Magnetic Signature Length) parameters. The
accuracy achieved with this method was 89%. In the other method, vehicle
classification was performed using machine learning algorithm J48 which is a
machine learning decision tree extension and the obtained results were
optimized based on the proposed method. It uses the J48 classification
algorithm implemented in Weka, a machine learning software package. The
Decision Tree model was built from a series of features like magnetic raw data,
measurement time derived from vehicles passing through the 3-axis HMC5983L
magnetic sensor. The properties are those provided by the correct
classification into the J48 training algorithm to produce a decision tree model
with grading ratios that vary on the basis of cross validity. The use of J48, a
machine learning algorithm, has been shown to yield more efficient and accurate
results in vehicle classification. The MSL values obtained by the first method
have caused difficulties in the calculation process. However, by using the J48
algorithm, more specific and sensitive boundary and threshold values were
obtained. The result of the study illustrates that the vehicle classification
system is so effective and efficient with an accuracy rate of about 100% with
optimization of the proposed system.

Keywords

Wireless sensor networks, Magnetic sensor, Vehicle classification, Machine learning algorithm, Magnetic signature length

References

• Haoui A, Kavaler R, Varaiya P. “Wireless magnetic sensors for traffic surveillance”. Transportation Research Part C: Emerging Technologies, 16(3), 294-306 2008.
• Lei Z, Wang R, Cui L. “Real-time traffic monitoring with magnetic sensor networks”. Journal of information science and engineering, 27(4), 1473-1486 2011.
• Gil Jimenez VP, Fernandez JM. “Simple design of wireless sensor networks for traffic jams avoidance”. Journal of Sensors, 2015(1), 1-7 2015.
• Nooralahiyan AY, Kirby HR, McKeown D. “Vehicle classification by acoustic signature”. Mathematical and Computer Modelling, 27(9), 205–214 1998.
• Jo Y, Jung I. “Analysis of vehicle detection with wsn-based ultrasonic sensors”. Sensors, 14(8), 14050-14069 2014.
• Leitloff J, Rosenbaum D, Kurz F, Meynberg O, Reinartz P. “An operational system for estimating road traffic information from aerial images”. Remote Sensing, 6(11), 11315-11341 2014.
• Barbagli B, Manes G, Facchini R, Manes A. “Acoustic sensor network for vehicle traffic monitoring”. 1st International Conference on Advances in Vehicular Systems, Technologies and Applications, Venice, Italy, 24-29 June 2012.
• Chen W, Chen L. “A Realtime dynamic traffic control system based on wireless sensor network”. In Proceedings of the 2005 International Conference on Parallel Processing Workshops (ICPPW’05), Oslo, Norway, 14-17 June 2005.
• Nadeem T, Dashtinezhad S, Liao C, Iftode L, “TrafficView: a scalable traffic monitoring system”. IEEE International Conference on Mobile Data Management (MDM’04), Berkeley, USA, 19-22 January 2004.
• Ng EH, Tan SL, Guzman JG. “Road traffic monitoring using a wireless vehicle sensor network”. International Symposium on Intelligent Signal Processing and Communication System, Bangkok, Thailand, 8-11 December, 2008.
• Haijian L, Honghui D., Limin J. Moyu R. “Vehicle classification with single multi-functional magnetic sensor and optimal MNS-based CART”. Measurement, 55(2), 142-152 2014.
• Lifu W, Nong Z, Haiping D. “Real-time identification of vehicle motion-modes using neural networks”. Mechanical Systems and Signal Processing, 51, 632-645 2015.
• Dogan R, Erdem E. “Temperature and humidity control of the tunnels in the dam using wireless sensor networks”. 19th International Conference on Intelligent Engineering Systems, Bratislava, Slovakia, 3-5 September 2015.
• Cheung SY, Coleri S, Dundar B, Ganesh S, Tan CW, Varaiya P. “Traffic Measurement and Vehicle Classification with a Single Magnetic Sensor”. California PATH Research Report UCB-ITS-PWP-2004-7 2004.
• Vancin S, Erdem E. “Design and simulation of wireless sensor network topologies using zigbee standard”. International Computer Networks and Applications, 2(3), 135-143 2015.
• Mihajlov B, Bogdanoski M. “Overview and analysis of the performances of Zigbee based wireless sensor networks”. International Journal of Computer Applications, 29(12), 28-35 2011.
• Wang X, Zhang S. “Comparison of several sensor deployments in wireless sensor networks”. International Conference on E-Health Networking, Digital Ecosystems and Technologies, Shenzhen, China, 2010.
• Vancin S, Erdem E. “Kablosuz manyetik sensör ağlarinda adaptif eşik değer algoritmasiyla araç tespitinin gerçekleştirilmesi”. International Artifical Intelligence and Data Mining Symposium, Inonu University, Malatya, Turkey, 17-18 September 2016.
• Gans JS, King SP, Wright J. Wireless communications. ISBN:0444514236, Handbook of Telecommunications Economics, 2005.
• Chang K. RF and Microwave wireless systems”. ISBNs: 0-471-35199-7, John Wiley & Sons, Ltd 2000.
• Karasulu B, Toker L, Korukoğlu S. “ZigBee - IEEE 802.15.4 Standard based wireless sensor networks”. Int. Conf., Information Üniv., İstanbul, Turkey 2009.
• Markevicius V, Navikas D, Daubaras A, Cepenas, ZMM, Andriukaitis D. “Vehicle influence on the earth’s magnetic field changes”. Elektronika IR, Elektrotechnika, 20(4), 43-48 2014.
• Ciureanu P, Middelhoek S. Thin Film Resistive Sensors. 1st ed. New York, USA, CRC Press, 1992.
• Jonasson C, Erlandsson M, Johansson C. “Magnetic Sensors for Traffic Detection”. IMEGO, Technical Report, Sweden 2006.
• Jo Y, Jung I. “Analysis of vehicle detection with wsn-based ultrasonic sensors”. Sensors, 14(8), 14050-14069, 2014.
• Michael JC, Withanawasam LS. “Vehicle detection and compass applications using AMR magnetic sensors”. Honeywell, SSEC, 12001 State Highway 55, Plymouth. MN USA 55441 1999.
• Piecha J. “Digital camera as a data source of its solution in traffic control and management”. Transport Problems. 7(4), 57-70 2012.
• Bottero M, Dalla CB, Deflorio FP. “Wireless sensor networks for traffic monitoring in a logistic centre”. Transportation Research Part C: Emerging Technologies. 26, 99-124 2013.
• Sifuentes E, Casas O, Pallas-Areny R. “Wireless magnetic sensor node for vehicle detection with optical wake-up”. IEEE Sensors Journal, 11(8), 1669-1676 2011.
• Zhou JC, Chen LP, Chen L. “A small-scale traffic monitoring system in urban wireless sensor networks”. IEEE International Conference on Systems, Man, and Cybernetics (SMC '13), Manchester, United Kingdom, 13-16 October 2013.
• Vancin S. Trafik Izleme Sistemlerinin Kablosuz Manyetik Sensörler Kullanılarak Gerçekleştirilmesi. Yüksek Lisans Tezi, Fırat Üniversitesi, Elazığ, Türkiye, 2016.
• Fernãndez J, Calavia L, Baladrón C. “An intelligent surveillance platform for large metropolitan areas with dense sensor deployment”. Sensors, 13(6), 7414–7442 2013.
• Ying K, Ameri A, Trivedi A, Ravindra D, Patel D, Mozumdar M. “Decision tree-based machine learning algorithm for in-node vehicle classification”. Department of Electrical Engineering, California State University, Long Beach 2015.
• Al-Nasser FA, Mahmoud MS. “Wireless sensors network application: a decentralized approach for traffic control and management in wireless sensor networks”. Technology and Applications, 16, 347–374 2012.